Causal-Model-Based Stress Testing of Anti Money Laundering Policies and Their Impact on Financial

This paper develops a structural causal model to quantify how anti-money-laundering (AML) policy adjustments influence both detection performance and financial-system stability. The model integrates regulatory thresholds, monitoring rules, bank-level reporting behaviors, and macro-prudential indicators. Panel data from 23 banks over 10 years, comprising 1.2 billion transactions, were used for parameter estimation and scenario simulation. Tightening suspicious-activity thresholds increased estimated detection rates by 18–24% but reduced liquidity coverage ratios by up to 3.6% for smaller institutions. A balanced scenario combining moderate threshold adjustments with targeted monitoring improved detection by 15.0% while limiting liquidity impact to 1.1%. The framework quantitatively illustrates the trade-off between surveillance strength and system-wide stability.